Model comparison
DeepSeek LLM 67B vs Llama 3.2 3B
Llama 3.2 3B is the stronger model overall, scoring 28.9 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
MetaSummary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 3 categories and Llama 3.2 3B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 3.2 3B leads 32.4 to 8.7.
Side by side
| DeepSeek LLM 67B | Llama 3.2 3B | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 24.9 | 28.9 |
| Released | 2023-11-29 | 2024-09-24 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 118K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 15 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek LLM 67B leads
DeepSeek LLM 67B: 31.9 (#278), Llama 3.2 3B: 27.6 (#319)
| Benchmark | DeepSeek LLM 67B | Llama 3.2 3B |
|---|---|---|
| LMArena Coding | 1096 | 1098 |
| BigCodeBench Instruct | — | 23.4% |
| BigCodeBench Complete | — | 28.3% |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Llama 3.2 3B: 20.1 (#143)
| Benchmark | DeepSeek LLM 67B | Llama 3.2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 21.9% |
| BALROG | — | 10.1% |
Reasoning Llama 3.2 3B leads
DeepSeek LLM 67B: 16.5 (#304), Llama 3.2 3B: 21.0 (#228)
| Benchmark | DeepSeek LLM 67B | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1095 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math Llama 3.2 3B leads
DeepSeek LLM 67B: 8.7 (#324), Llama 3.2 3B: 32.4 (#214)
| Benchmark | DeepSeek LLM 67B | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1108 | 1126 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Llama 3.2 3B leads
DeepSeek LLM 67B: 7.0 (#313), Llama 3.2 3B: 29.7 (#235)
| Benchmark | DeepSeek LLM 67B | Llama 3.2 3B |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1090 |
Multilingual DeepSeek LLM 67B leads
DeepSeek LLM 67B: 29.4 (#267), Llama 3.2 3B: 26.2 (#281)
| Benchmark | DeepSeek LLM 67B | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1073 | 1019 |
| LMArena Chinese | 1132 | 1017 |
| LMArena German | — | 1056 |
| LMArena Russian | — | 949 |
Instruction Following Too close to call
DeepSeek LLM 67B: 55.4 (#277), Llama 3.2 3B: 56.0 (#275)
| Benchmark | DeepSeek LLM 67B | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1079 | 1089 |
Long Context Too close to call
DeepSeek LLM 67B: 33.1 (#265), Llama 3.2 3B: 33.4 (#261)
| Benchmark | DeepSeek LLM 67B | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1092 | 1100 |
Writing & Preference DeepSeek LLM 67B leads
DeepSeek LLM 67B: 31.6 (#282), Llama 3.2 3B: 24.7 (#307)
| Benchmark | DeepSeek LLM 67B | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1105 | 1110 |
| LMArena Creative Writing | 1067 | 1094 |
| LMArena Multi-Turn | 1082 | 1105 |
| EQ-Bench Creative Writing | — | 595 |
Frequently asked questions
Is DeepSeek LLM 67B better than Llama 3.2 3B?
Llama 3.2 3B is the stronger model overall, scoring 28.9 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Llama 3.2 3B better for coding?
DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 27.6 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Llama 3.2 3B share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Llama 3.2 3B has 18.